npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@siyuqian/flow-engine

v0.1.1

Published

Fully automated spec-driven development workflow built on OpenSpec

Readme

flow-engine

Fully automated spec-driven development workflow built on OpenSpec.

Write a spec with AI, then walk away — flow-engine handles implementation, testing, verification, and review automatically.

How It Works

[You + AI]                              [Fully Automated]
propose → specs → design → tasks   →   implement → test → verify → review
  1. You write a spec with AI using OpenSpec's standard workflow (/opsx:propose)
  2. You trigger apply (/opsx:apply) and walk away
  3. AI executes the full pipeline — implements code, generates tests, runs multi-layer verification, produces a final review report
  4. You come back and read the report. Fix any TODOs. Archive.

When AI encounters uncertainty, it follows a 4-level protocol: research the codebase → search the web → run experiments → fallback with TODO. It only stops when nothing else can be tried.

Prerequisites

  • Node.js >= 20
  • OpenSpec CLI installed globally:
    npm install -g openspec
  • An IDE with an AI agent that supports OpenSpec slash commands (Claude Code, Cursor, etc.)

Installation

npx github:siyuqian/flow-engine init

This command:

  1. Initializes OpenSpec in your project (if not already done)
  2. Installs the flow-engine custom schema with automation templates
  3. Sets flow-engine as the default schema

Usage

1. Start a new change (in your IDE)

> /opsx:propose add-user-auth

AI collaborates with you to create:

  • proposal.md — why this change is needed
  • specs/ — requirements with Given/When/Then scenarios
  • design.md — technical approach
  • tasks.md — implementation checklist

Review and approve these before continuing.

2. Run the automated pipeline (in your IDE)

> /opsx:apply

AI automatically executes:

| Stage | What it does | Output | |-------|-------------|--------| | Implement | Writes code for each task | implement-report.md + code changes | | Test | Generates tests from spec scenarios, runs them | test-report.md + test files | | Verify | 3-layer check: tests, spec alignment, code review | verify-report.md | | Review | Final summary with human action items | review-report.md |

3. Check results

openspec status --change add-user-auth

Read the reports directly:

  • openspec/changes/add-user-auth/review-report.md — start here
  • openspec/changes/add-user-auth/verify-report.md — verification details
  • openspec/changes/add-user-auth/test-report.md — test results

4. Archive when done

> /flow-engine:archive add-user-auth

Delta specs merge into your main specs. The change (with all reports) moves to archive.

After archiving, you'll be prompted to update project documentation:

> /flow-engine:update-docs add-user-auth

This reviews README.md, CLAUDE.md, and AGENTS.md against the archived change and suggests updates. You can also run it independently at any time for a full documentation review:

> /flow-engine:update-docs

Resuming After Interruption

If the pipeline is interrupted (IDE crash, token limit, etc.), just re-run /opsx:apply. The AI checks which report files exist and resumes from where it left off.

CLI Commands

# Initialize flow-engine in a project
npx github:siyuqian/flow-engine init

# All OpenSpec CLI commands are proxied:
npx github:siyuqian/flow-engine list
npx github:siyuqian/flow-engine show <name>
npx github:siyuqian/flow-engine status --change <name>
npx github:siyuqian/flow-engine validate
npx github:siyuqian/flow-engine archive <name>
npx github:siyuqian/flow-engine schema <subcommand>

Custom Schema

flow-engine extends OpenSpec's spec-driven schema with 4 automated stages. The schema and templates are installed in your project at openspec/schemas/flow-engine/.

You can customize the templates to adjust automation behavior — they are plain markdown files that instruct the AI agent.

License

MIT